←back to thread

MCP is eating the world

(www.stainless.com)
335 points emschwartz | 3 comments | 21 Jun 25 16:30 UTC | HN request time: 0.629s | source
Show context
faxmeyourcode ◴[24 Jun 25 16:58 UTC] No.44368295[source]▶
Based on the comments here, a lot of folks are assuming the primary users of mcp are the end users connecting their claude/vscode/etc to whatever saas platform they're working on. While this _is_ a huge benefit and super cool to use, imo the main benefit is for things like giving complex tool access to centralized agents. Where the mcp servers allow you to build agents that have the tools to do a sort of "custom deep research."

We have deployed this internally at work where business users are giving it a list of 20 jira tickets and asking it to summarize or classify them based on some fuzzy contextual reasoning found in the description/comments. It will happly run 50+ tool calls poking around in Jira/confluence and respond in a few seconds what would have taken them hours to do manually. The fact that it uses mcp under the hood is completely irrelevant but it makes our job as builders much much easier.

replies(7): >>44368648 #>>44368903 #>>44368929 #>>44368954 #>>44369304 #>>44374580 #>>44375982 #
tptacek ◴[24 Jun 25 18:00 UTC] No.44368929[source]▶
I'm doing the same thing now (with Slack as a medium of interaction with the agent) --- but not with MCP, just with straight up tool call APIs.
replies(1): >>44369521 #
rattray ◴[24 Jun 25 18:50 UTC] No.44369521[source]▶
How many tools does your agent have access to?

At Stainless we use https://github.com/dgellow/mcp-front to make it easy for anyone on the team (including non-technical folks) to OAuth into a pretty wide variety of tools for their AI chats, using their creds. All proxied on infra we control.

Even our read replica postgres DB is available, just push a button.

replies(1): >>44369562 #
1. tptacek ◴[24 Jun 25 18:53 UTC] No.44369562[source]▶
Just 5 or 6. I'm just using the OpenAI tool call API for it; I own the agent (more people should!) so MCP doesn't do much for me.
replies(1): >>44371724 #
2. fb03 ◴[24 Jun 25 22:31 UTC] No.44371724[source]▶
This. If you are running your agent loop, MCP does nothing.

MCP is an inter-process (or inter-system) communication standard, and it's extremely successful at that. But some people try to shoehorn it into a single system where it makes for a cumbersome fit, like having your service talk to itself via MCP as a subprocess just for the sake of "hey, we have MCP".

If you own your loop AND your business logic lives in the same codebase/process as your agent loop, you don't need MCP at all, period. Just use a good agent framework like PydanticAI, define your tools (and have your framework forward your docstrings/arguments into the context) and you're golden!

replies(1): >>44398524 #
3. easypancakes ◴[27 Jun 25 17:15 UTC] No.44398524[source]▶
Hi! I am a bit lost in all of this. How do you create your own agent and run your own loop? I've looked at PydanticAI but don't get it. Would you please give me an example? Thanks!